Large language model integrations in cancer decision-making: a systematic review and meta-analysis
Интеграция больших языковых моделей в принятие решений в онкологии: систематический обзор и метаанализ
2025-07-17
SCID: 54.1/86jafb9b
Discuss with AI
cancer decision-makingdiagnostic accuracylarge language modelsoncologysystematic review and meta-analysis
Figures from the paper
Abstract (AI)
Large Language Models (LLMs) are increasingly used to support cancer patients and clinicians in decision-making. This systematic review investigates how LLMs are integrated into oncology and evaluated by researchers. We conducted a comprehensive search across PubMed, Web of Science, Scopus, and the ACM Digital Library through May 2024, identifying 56 studies covering 15 cancer types. The meta-analysis results suggested that LLMs were commonly used to summarize, translate, and communicate clinical information, but performance varied: the average overall accuracy was 76.2%, with average diagnostic accuracy lower at 67.4%, revealing gaps in the clinical readiness of this technology. Most evaluations relied heavily on quantitative datasets and automated methods without human graders, emphasizing "accuracy" and "appropriateness" while rarely addressing "safety", "harm", or "clarity". Current limitations for LLMs in cancer decision-making, such as limited domain knowledge and dependence on human oversight, demonstrate the need for open datasets and standardized evaluations to improve reliability.
Key Findings
1
A systematic review identified 56 studies examining LLM integration into oncology decision-making across 15 cancer types.
2
Average overall accuracy was 76.2%, while average diagnostic accuracy was lower at 67.4%, indicating limited clinical readiness.
3
Evaluations predominantly used quantitative datasets and automated methods, rarely involving human graders or assessing safety, harm, and clarity.
4
LLMs were primarily used to summarize, translate, and communicate clinical information for cancer-related decision-making.
5
Limited oncology-specific knowledge and reliance on human oversight highlight the need for open datasets and standardized evaluation frameworks.
Research Object
Large Language Models integrated into oncology/cancer decision-making
Research Subject
Their clinical decision-support uses, performance, evaluation criteria, and limitations in cancer care
Publication Details
Publication Date
2025-07-17
Journal
Publisher
ISSN
Cited by
69
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns2023
Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine2023
The future landscape of large language models in medicine2023
A framework for human evaluation of large language models in healthcare derived from literature review2024